AI/rocm-systems
2
0
Fork 0
Código Issues Pull Requests Ações Pacotes Projetos Versões Wiki Atividade
63 Commits 3 Branches 0 Tags
cd0589ff02100a5838d6e4b10fee022db20f7883
Gráfico de Commits

54 Commits

Autor SHA1 Mensagem Data
Aditya Atluri cd0589ff02 added sample for how-to-use pre-compiled kernels1. Corrected the exit output of kernel compilation by hipcc 
2. Added sample which loads/run kernel binary during runtime?

Change-Id: I26ccaca1f844fee317592e26c9e654ce548b96a8


[ROCm/hip-tests commit: c1b1086c71]
 2016-08-31 13:56:07 -05:00
Maneesh Gupta e18a65c1d7 Rename 2_Advanced to 7_Advanced 
Change-Id: I51e5fa7f4c1dbf467f2d7182ec69d12d5fe548d0


[ROCm/hip-tests commit: 6ad8ac5d95]
 2016-08-18 12:40:30 +05:30
Maneesh Gupta 54d1f14ae0 Add simple hipblas saxpy sample 
Change-Id: I67ae83e1e5397d5191a3c644aba068f06ff97830


[ROCm/hip-tests commit: 339590da90]
 2016-08-12 13:50:22 +05:30
Maneesh Gupta ce24bbe845 hipDispatchLatency: reduce iterations to 5120 
Change-Id: I94ae4993ff5058cf15f9487a5a528fc24c1ad5fa


[ROCm/hip-tests commit: a685f7dc79]
 2016-06-13 14:23:51 +05:30
Maneesh Gupta ad1c6108ae Fix bit_extract sample 
Change-Id: I933f932bac26d9a9469d5d069973af166e11cbcd

[ROCm/hip-tests commit: e89fba7fe1]
 2016-05-20 01:06:08 -04:00
Maneesh Gupta 3db5dd362c Fix square.cu to use cudaError_t instead of hipError_t 
Change-Id: If3314910d1c03122741d3e0a45e14a4412c473b3


[ROCm/hip-tests commit: f6544a376b]
 2016-05-12 10:13:07 +05:30
Maneesh Gupta e5cabc4a4d hcc_dialects report PASSED when passed 
[ROCm/hip-tests commit: 07026bfdea]
 2016-05-03 14:32:59 +05:30
Maneesh Gupta df93c6a288 bit_extract reports PASSED when passed 
[ROCm/hip-tests commit: fb88bb1c17]
 2016-05-03 14:19:25 +05:30
Maneesh Gupta 52022d72d4 Fix makefiles in samples 
[ROCm/hip-tests commit: 307b24b9d5]
 2016-04-18 10:15:35 +05:30
Maneesh Gupta cb0c7b71a7 Replace /opt/hcc -> /opt/rocm/hcc and /opt/hsa -> /opt/rocm/hsa 
[ROCm/hip-tests commit: 4092a1efe8]
 2016-04-15 12:56:31 +05:30
Ben Sander 5dda7686cb Fix HIP_PATH, CHECK macro in samples. 
[ROCm/hip-tests commit: 40e3772d40]
 2016-04-13 17:37:39 -05:00
Ben Sander a8ddf0d4c5 add hcc dialects sample 
[ROCm/hip-tests commit: a296b93281]
 2016-04-13 17:32:38 -05:00
Ben Sander f268a705ee fix peer query order 
[ROCm/hip-tests commit: 7eba742c66]
 2016-04-11 07:58:59 -05:00
Ben Sander 9c9047deb2 P2p checkpoint. 
- set USE_PEER_TO_PEER=3 (requires HCC "am_memtracker_update_peers")
- when enabling peer, turn it on for previously allocated memory.
- hipDeviceCanAccessPeer is no longer self-ware (self does not qualify
  as a peer)
- device peerlist always includes self, so when we call allow_access
  we never remove self access.
- hipDeviceReset() removes old peer mappings.


[ROCm/hip-tests commit: c161c1ba9b]
 2016-04-11 07:58:59 -05:00
Ben Sander 41adba3869 Remove stray debug msgs, hipInfo don't print self as peer. 
[ROCm/hip-tests commit: 565300acb0]
 2016-04-11 07:58:58 -05:00
Ben Sander 90522e6e1b Use HIP_PATH if set else use relative ../... 
[ROCm/hip-tests commit: 2fd45f0a6d]
 2016-04-11 07:58:58 -05:00
Ben Sander 1bc31374a1 Print peers in hipConfig. 
Also include peer APIs in vim hilighting.


[ROCm/hip-tests commit: 4fca0a1bdf]
 2016-04-11 07:58:58 -05:00
Maneesh Gupta 6d4cf596db Remove deprecated KERNELBEGIN and KERNELEND from bit_extract sample 
[ROCm/hip-tests commit: 2433bca2b1]
 2016-04-04 14:47:02 +05:30
streamhsa f2f6e3166a change makefile for samples 
[ROCm/hip-tests commit: 155c366e79]
 2016-03-29 16:02:09 +08:00
Aditya Atluri 62f12b2eeb Logging dispatch latency through database util 
[ROCm/hip-tests commit: 4992ccfea6]
 2016-03-23 11:39:57 -05:00
Ben Sander e64947ab4f Only include activity logger if CodeXL installed. 
Fix hipHostMalloc in hipBusBandwidth.


[ROCm/hip-tests commit: c1dd930c92]
 2016-03-22 09:27:10 -05:00
Ben Sander 173e850976 hipHostRegister and hipHostMalloc refactor. 
Note hipHostMalloc (not hipHostAlloc or hipMallocHost).
 -  the hipHost* is used for all HIP APIs dealing with Host memory.
    (including hipHostMalloc, hipHostFree, hipHostRegister,
hipHostUnregister, hipHostGetFlags, hipHostGetDevicePointer).
  - hipMallocHost is consistent with "hipMalloc" for allocating device
    memory.  Enumerations hipHostMalloc* also used as optional
    flags parm to hipHostMalloc.


[ROCm/hip-tests commit: 3b3bae3772]
 2016-03-22 02:30:10 -05:00
Ben Sander c7d2605a37 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 
Conflicts:
	src/hip_hcc.cpp


[ROCm/hip-tests commit: 221973404f]
 2016-03-19 03:22:09 -05:00
Ben Sander 3097de0b0e Add beastperiteration and onesize for testing. 
onesize allows running tests at one specific size.


[ROCm/hip-tests commit: d011d7cf6e]
 2016-03-19 02:43:04 -05:00
Ben Sander 99b2af44ae Improve formatting - line up cols 
[ROCm/hip-tests commit: f7e2c254df]
 2016-03-18 23:43:04 -05:00
Ben Sander 9ca75a115b Print Pinned or Unpinned in result summary 
[ROCm/hip-tests commit: 62fb06f54e]
 2016-03-18 21:28:29 -05:00
Ben Sander bffe0bd7ac Supported --aliged mode. Add results check for H2D and D2H. 
[ROCm/hip-tests commit: 97493d2098]
 2016-03-18 03:09:52 -05:00
Aditya Atluri d3509b4b0f corrected first and second kernel dispatch 
[ROCm/hip-tests commit: 9800567a53]
 2016-03-15 14:22:00 -05:00
Aditya Atluri 9874d352bf Added single kernel launch to sample 
[ROCm/hip-tests commit: f10d879285]
 2016-03-15 21:05:15 -05:00
Aditya Atluri 6009d12697 added performance metrics for kernel dispatch 
[ROCm/hip-tests commit: 93c30afe2f]
 2016-03-15 12:37:24 -05:00
Aditya Atluri 2a6922c4d9 v2 deprecating hipMallocHost with hipHostAlloc 
[ROCm/hip-tests commit: e376b1baec]
 2016-03-15 13:39:15 -05:00
Ben Sander 96eab48c52 print device config info 
[ROCm/hip-tests commit: 6b34ae4797]
 2016-03-14 23:02:49 -05:00
Ben Sander f5b47e9c92 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 
Conflicts:
	src/hip_hcc.cpp
	tests/src/CMakeLists.txt


[ROCm/hip-tests commit: 3c2c2e02eb]
 2016-03-14 15:01:26 -05:00
Ben Sander 65314478a4 Add Bidir copy test and help. 
[ROCm/hip-tests commit: 65f40e68c8]
 2016-03-14 14:39:23 -05:00
Ben Sander bb101380c4 refactor, add support for speccing xfers in bytes 
[ROCm/hip-tests commit: f5849f462e]
 2016-03-13 09:41:06 -05:00
Aditya Atluri 0d32a4fecb corrected hipDeviceGetProperties to hipGetDeviceProperties - not docs 
[ROCm/hip-tests commit: 0155e5b879]
 2016-03-06 08:31:04 -06:00
Ben Sander 4d58d5e7cf fixes for titan platform 
[ROCm/hip-tests commit: 2fb97ae4d8]
 2016-02-26 05:25:30 -06:00
Ben Sander 8a0bb5a000 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 
[ROCm/hip-tests commit: 2a15579db0]
 2016-02-26 06:15:09 -06:00
Ben Sander 2527618036 Merge branch 'memtracker' into privatestaging 
Conflicts:
	src/hip_hcc.cpp


[ROCm/hip-tests commit: 7e25c52055]
 2016-02-25 19:38:46 -06:00
Evgeny Mankov 7af6946c0e Attribute hipDeviceAttributeIsMultiGpuBoard for obtaining Device property isMultiGpuBoard is added. 
On HIP path property obtaining done through hsa_iterate_agents and counting the devices of HSA_DEVICE_TYPE_GPU type.

P.S.
On multi-boards systems it might be problems with detection what board a GPU plugged into (not tested).


[ROCm/hip-tests commit: 11b75c38de]
 2016-02-25 23:44:39 +03:00
Evgeny Mankov 71c61a600e Guard #ifdef USE_ROCR_20 is added for ROCR_20 device properties (memoryClockRate, memoryBusWidth) 
By default isn't defined.
To add ROCR_20 support HIP have to be compiled as follows: make CXX_DEFINES+=-DUSE_ROCR_20


[ROCm/hip-tests commit: bdb6c4f423]
 2016-02-19 13:27:03 +03:00
Evgeny Mankov e491a659fe Device property memoryBusWidth implementation. 
+ Device property memoryBusWidth is added to hipDeviceProp_t struct.
+ Device attribute hipDeviceAttributeMemoryBusWidth is added to hipDeviceAttribute_t struct.
+ Tests update.


[ROCm/hip-tests commit: 83612db41b]
 2016-02-18 18:15:01 +03:00
Evgeny Mankov 00ce9647c7 Device property memoryClockRate implementation. 
+ Device property memoryClockRate is added to hipDeviceProp_t struct.
+ Device attribute hipDeviceAttributeMemoryClockRate is added to hipDeviceAttribute_t struct.
+ Tests update.
+ Rename hipDevAttrConcurrentKernels to hipDeviceAttributeConcurrentKernels.


[ROCm/hip-tests commit: 383310d9d0]
 2016-02-18 17:25:28 +03:00
Evgeny Mankov 7ac40d9ca5 hipInfo sample update with new Device Properties. 
[ROCm/hip-tests commit: ff22a6eb28]
 2016-02-18 15:08:55 +03:00
Evgeny Mankov d2a67588d0 Formatting, no functional changes. 
[ROCm/hip-tests commit: 12fcf1d0ff]
 2016-02-15 13:16:05 +03:00
Ben Sander a776b6c7c3 Enable -O3, style points on array size 
[ROCm/hip-tests commit: f12a1e9581]
 2016-02-13 03:17:42 -06:00
Ben Sander 931a24bad1 Result formatting 
[ROCm/hip-tests commit: b5743abae2]
 2016-02-13 01:14:01 -06:00
Ben Sander 19c6c95b8e Add D2H test 
[ROCm/hip-tests commit: 63d79554ab]
 2016-02-12 22:47:26 -06:00
Ben Sander 4b0bf5c1a1 Add D2H test 
[ROCm/hip-tests commit: 42257c5d71]
 2016-02-12 22:46:34 -06:00
Ben Sander cb84597d5e Add Bus Bandwidth test, leveraged from SHOC. 
[ROCm/hip-tests commit: 8cb885f03a]
 2016-02-12 21:30:43 -06:00